Node.js Library

Node.js library for Akkio

API Keys

As noted in the code samples below, you must get your API keys and copy them into your API code. Those can be found under the team settings page at the bottom of the Akkio app.

Installation

npm install --save akkio

Example Usage

# get your API key at https://app.akkio.com/team-settings
const akkio = require('akkio')('your API key');

(async () => {
  # create a new dataset
  let newDataset = await akkio.createDataset('my new dataset');

  # populate it with some toy data
  let rows = [];
  for (var i = 0; i < 1000; i++) {
    let x = Math.random();
    rows.push({
      'x': x,
      'value larger than 0.5': x > 0.5,
    });
  }
  await akkio.addRowsToDataset(newDataset.dataset_id, rows);

  # train a model
  let model = await akkio.createModel(newDataset.dataset_id, ['value larger than 0.5'], [], {
    duration: 1
  });

  # field importance
  for (let field in model.field_importance) {
    console.log('field:', field, 'importance:', model.field_importance[field]);
  }

  # model stats
  for (let field of model.stats) {
    for (let outcome of field) {
      console.log(outcome);
    }
  }

  # use the trained model to make predictions
  let predictions = await akkio.makePrediction(model.model_id, [{
    'x': 0.25
  }, {
    'x': 0.75
  }], {
    explain: true
  });
  console.log(predictions);

})();

Datasets

createDataset(dataset_name)

Create a new empty dataset.

input	description
dataset_name	The name of your newly created dataset.

addRowsToDataset(dataset_id, rows)

Add rows to a dataset.

input	description
dataset_id	A dataset id
rows	An array of rows to be added to the dataset in the following form: [{ "field 1": "data", "field 2": "data" }, { ... }, ... ]

getDatasets()

Get all datasets in your organization.

getDataset(dataset_id)

Get a dataset.

input	description
dataset_id	A dataset id

parseDataset(dataset_id)

Recalculate the field types for a dataset.

input	description
dataset_id	A dataset id

deleteDataset(dataset_id)

Delete a dataset.

input	description
dataset_id	A dataset id

Models

getModels()

Get all models in your organization.

deleteModel(model_id)

Delete a model in your organization.

input	description
model_id	A model id

createModel(dataset_id, predict_fields, ignore_fields, params)

Create a model (requires a dataset).

input	description
dataset_id	A dataset id
predict_fields	An array of field names to predict (case sensitive)
ignore_fields	An array of field names to ignore (case sensitive) (optional)
params	A dict with default value of: { "duration": 10, "extra_attention: false, "force": false } duration is the duration in seconds to be used for model training. extra_attention can be enabled to help with predicting rare cases force forces a new model to be created

Sometimes creating models can take a while, especially if this is the first time creating a model on this dataset. createModel is idempotent and can be called multiple times with the same parameters.

makePrediction(model_id, data)

Make a prediction using your model and new data.

input	description
model_id	A model id
data	An array of rows to be predicted in the following form: [{ "field 1": "data", "field 2": "data" }, { ... }, ... ]